abhinavp's picture
Training in progress, epoch 1, checkpoint
4c6ba61 verified
{
"best_metric": 4.040642738342285,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/re-irr-sv-agr/transformer/4/checkpoints/checkpoint-152640",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 152640,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 11.009,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8095,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1651,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9594,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.7982,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.694,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5853,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5267,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4291,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3859,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3256,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2522,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.1968,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1645,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1134,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.089,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0669,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0378,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0085,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 4.9983,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9686,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9489,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9122,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9128,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8816,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8695,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8503,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8233,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8105,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7914,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7841,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7687,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7612,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7491,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7362,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7235,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.6883,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.6873,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6762,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6602,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6636,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6576,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6361,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6361,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6288,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6205,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6164,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5972,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5849,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.5868,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5729,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5727,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 4.5461,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5598,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.5338,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5539,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5278,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5255,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.518,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.513,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.4991,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5042,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4797,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4747,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.4883,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.48,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4671,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4529,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4541,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4609,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 4.4558,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4483,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4451,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4465,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4403,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4182,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.42,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4199,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4095,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4097,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4036,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4193,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.3935,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3795,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.3901,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.3872,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.3929,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3719,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3744,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3727,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3668,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3566,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.3593,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.3604,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3678,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3472,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3402,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3392,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3386,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3461,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3322,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.3259,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3194,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3281,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.2985,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.3173,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3088,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.315,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3032,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3084,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.2974,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.2982,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3028,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.2857,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3022,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.2988,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.2908,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.2812,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.2801,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.2832,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.2801,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.2792,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.268,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.2754,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2601,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2638,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2515,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2554,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2437,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2666,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2705,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2571,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2336,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.2548,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.2475,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2457,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2374,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2459,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2392,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2337,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2348,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.2369,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.223,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.225,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.237,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2213,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.2224,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.2328,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.2133,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.207637310028076,
"eval_runtime": 302.2209,
"eval_samples_per_second": 1262.623,
"eval_steps_per_second": 39.458,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.1968,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2045,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2192,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.2089,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.2145,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.192,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.2047,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.1838,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.2006,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.1845,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.2007,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.1956,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.1857,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.1773,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.1703,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.1704,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.1794,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.177,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.169,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858326623483405e-05,
"loss": 4.1887,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.1814,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856649433981301e-05,
"loss": 4.1729,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855810839230249e-05,
"loss": 4.164,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.1831,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.1552,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.1677,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.1657,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.1584,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.1492,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.1501,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.1548,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.1533,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.1539,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.1527,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.8457526158587444e-05,
"loss": 4.1513,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.8449140211076924e-05,
"loss": 4.1481,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440754263566404e-05,
"loss": 4.1318,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.137,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.1327,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.1284,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.1384,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.1396,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.1273,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.1265,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.1296,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.1312,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835692754606866e-05,
"loss": 4.1323,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834854159855814e-05,
"loss": 4.1226,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.1204,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.1243,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.1165,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.1194,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.1097,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.1225,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.0954,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.12,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.1087,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.106,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.1145,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.1009,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.0953,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823122022742952e-05,
"loss": 4.1112,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.0843,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.0861,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.1004,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.1008,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818930686868065e-05,
"loss": 4.0937,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818092092117013e-05,
"loss": 4.0827,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.084,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.0893,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155779457442305e-05,
"loss": 4.0975,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.0889,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.0939,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.0931,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122252046203954e-05,
"loss": 4.0939,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113866098693434e-05,
"loss": 4.075,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.0784,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.0866,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.076,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808033868745508e-05,
"loss": 4.0787,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807195273994456e-05,
"loss": 4.0716,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806356679243404e-05,
"loss": 4.0936,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805518084492352e-05,
"loss": 4.0728,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804681127621674e-05,
"loss": 4.0612,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803842532870622e-05,
"loss": 4.0729,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.80300393811957e-05,
"loss": 4.0741,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.0808,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.0644,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800489791746787e-05,
"loss": 4.0654,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799651196995735e-05,
"loss": 4.0744,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798812602244683e-05,
"loss": 4.0628,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.0584,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971370506229516e-05,
"loss": 4.0626,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7962984558718996e-05,
"loss": 4.0703,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954598611208476e-05,
"loss": 4.0701,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946212663697956e-05,
"loss": 4.0651,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793784309499117e-05,
"loss": 4.0488,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792945714748065e-05,
"loss": 4.0553,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792107119997013e-05,
"loss": 4.0571,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912685252459605e-05,
"loss": 4.0613,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790431568375282e-05,
"loss": 4.0571,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.78959297362423e-05,
"loss": 4.0518,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887543788731774e-05,
"loss": 4.0439,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879157841221254e-05,
"loss": 4.0589,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787078827251447e-05,
"loss": 4.026,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786240232500395e-05,
"loss": 4.0519,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854032756297166e-05,
"loss": 4.0421,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845646808786646e-05,
"loss": 4.0537,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837260861276126e-05,
"loss": 4.0394,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828874913765606e-05,
"loss": 4.0507,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782048896625508e-05,
"loss": 4.0389,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781210301874456e-05,
"loss": 4.0395,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803733450037775e-05,
"loss": 4.0488,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779534750252725e-05,
"loss": 4.036,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778696155501673e-05,
"loss": 4.0485,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777857560750621e-05,
"loss": 4.0522,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770206038799423e-05,
"loss": 4.0434,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761820091288903e-05,
"loss": 4.0349,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.7753434143778383e-05,
"loss": 4.0379,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774504819626786e-05,
"loss": 4.0406,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773666224875734e-05,
"loss": 4.0287,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772827630124682e-05,
"loss": 4.0446,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.77198903537363e-05,
"loss": 4.0282,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771150440622578e-05,
"loss": 4.0365,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770313483751899e-05,
"loss": 4.0311,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769474889000847e-05,
"loss": 4.027,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768636294249795e-05,
"loss": 4.0172,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767797699498743e-05,
"loss": 4.0242,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766960742628064e-05,
"loss": 4.016,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766122147877012e-05,
"loss": 4.037,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.76528355312596e-05,
"loss": 4.0458,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764444958374909e-05,
"loss": 4.0317,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.76360800150423e-05,
"loss": 4.0103,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762769406753178e-05,
"loss": 4.0325,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761930812002126e-05,
"loss": 4.0236,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761092217251074e-05,
"loss": 4.0272,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602552603803946e-05,
"loss": 4.0224,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594166656293426e-05,
"loss": 4.0245,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585780708782906e-05,
"loss": 4.0196,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577394761272386e-05,
"loss": 4.0208,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569025192565595e-05,
"loss": 4.0191,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560639245055075e-05,
"loss": 4.0241,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552253297544555e-05,
"loss": 4.0166,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754388372883777e-05,
"loss": 4.0099,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753549778132725e-05,
"loss": 4.0266,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752711183381673e-05,
"loss": 4.0186,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751872588630621e-05,
"loss": 4.0112,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751033993879569e-05,
"loss": 4.0261,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750195399128517e-05,
"loss": 4.0078,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.040642738342285,
"eval_runtime": 301.9306,
"eval_samples_per_second": 1263.837,
"eval_steps_per_second": 39.496,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.0296049351646822e+17,
"trial_name": null,
"trial_params": null
}